Anthropic: Claude Fable 5

by Anthropic

anthropic/claude-fable-5
Unavailable

Call Claude Fable 5 by Anthropic from Iran with one ir- key, paid in Rial. 27,319,435 IRR input and 136,597,175 IRR output per million tokens, 1M token context.

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

Context

1Mtokens

About 1,429 pages of text at once

Max output

128Ktokens

About 183 pages in one answer

Intelligence

—

No score published for this model.

Output speed

53tokens/s

A 500-word answer in about 13.1 s

From public market statistics for this model

First token

3.6s

Reasoning models start later

From public market statistics for this model

Health, 30 days

59.36%

1 of 30 days without a fault

IranRouter’s measurements

Price & cost

Every rate in Rial. A request pays only for the tokens it actually uses.

Input27,319,435IRR / 1M tokens
Output136,597,175IRR / 1M tokens
Reasoning tokensThe output rate136,597,175IRR / 1M tokens
Cache read2,731,944IRR / 1M tokens
Cache write, 5 minutes34,149,294IRR / 1M tokens
Cache write, 1 hour54,638,870IRR / 1M tokens
Image input tokensThe input rate27,319,435IRR / 1M tokens
Per web search27,319IRR

With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.

What would this model cost you a month?

Monthly cost

4.92BIRR

163.92M IRR a day, 82K IRR each request

30 days at today’s rate.

Rial price over 90 days

It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.

InputOutput

Performance, 30 days

Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.

Daily health59.36%

Time to first token3.91 s

Output speed54 tokens/s

Place in the market

By usage across the global model market.

Daily rank

Share of the day’s tokens

Capabilities

Image inputYes
Audio inputNo
Tool callingYes
JSON outputYes
ReasoningReasoning levels: max, xhigh, high, medium, low
Web searchNo
Prompt cacheYes
Makes imagesNo
Open weightsNo
On the free planNo
Input
TextImageFile
Output
Text

Parameters it accepts

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity

Other benchmarks

Design contests

  • Game devElo: 1,314Win rate: 61%
  • ASCII artElo: 1,312Win rate: 68%
  • UI componentsElo: 1,303Win rate: 58%
  • Data vizElo: 1,300Win rate: 58%
4 moreShow less
  • Code (overall)Elo: 1,294Win rate: 58%
  • SVGElo: 1,287Win rate: 63%
  • 3DElo: 1,284Win rate: 62%
  • WebsitesElo: 1,284Win rate: 56%

Standard tests

  • GPQA DiamondScore: 89%Tasks: 1,980
  • τ-bench Verified AirlineScore: 79%Tasks: 450

Start in a minute

The official OpenAI and Anthropic SDKs; only the address and the key change.

Base URLhttps://iranrouter.com/v1
Model IDanthropic/claude-fable-5
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://iranrouter.com/v1",
    api_key="ir-...",
)

r = client.chat.completions.create(
    model="anthropic/claude-fable-5",
    messages=[{"role": "user", "content": "Hello, introduce yourself"}],
)
print(r.choices[0].message.content)
The full guide in the docs: keys, streaming and errorsThe Claude API in Iran, priced in Rial

Peer models

Its family and models with a close score; the last column compares one message’s cost with this model.

No peer models found.

Technical specs

ID
anthropic/claude-fable-5
Maker
Anthropic
Tokenizer
Claude
Released
Jun 9, 2026
Added to IranRouter
Aug 14, 2026
Context
1,000,000 tokens
Max output
128,000 tokens

Scores by Design Arena, as of Nov 21, 2026

Anthropic: Claude Fable 5One message about 122,940 IRRStart with this model